Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 929 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.3047. Min Act: -0.1700

Data Index: 1559705 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.2587. Min Act: -0.1700

Data Index: 1443049 (Python Code)

Max Activating Token Index: 633

Text #2

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.2420. Min Act: -0.1700

Data Index: 1502868 (Python Code)

Max Activating Token Index: 523

Text #3

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.2275. Min Act: -0.1700

Data Index: 1431572 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.2096. Min Act: -0.1700

Data Index: 1504866 (Python Code)

Max Activating Token Index: 318

Text #5

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1701. Min Act: -0.1700

Data Index: 1562889 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1726. Min Act: -0.1700

Data Index: 1626410 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1683. Min Act: -0.1700

Data Index: 1634494 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1540360 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1306. Min Act: -0.1700

Data Index: 1275903 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1080. Min Act: -0.1700

Data Index: 1464998 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1226. Min Act: -0.1700

Data Index: 1597163 (Python Code)

Max Activating Token Index: 989

Text #12

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1246. Min Act: -0.1700

Data Index: 1644410 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1205. Min Act: -0.1700

Data Index: 1445968 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1087. Min Act: -0.1700

Data Index: 1364637 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1035. Min Act: -0.1700

Data Index: 1532623 (Python Code)

Max Activating Token Index: 443

Text #16

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.1022. Min Act: -0.1700

Data Index: 1426952 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.0911. Min Act: -0.1700

Data Index: 1395209 (Python Code)

Max Activating Token Index: 478

Text #18

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.0710. Min Act: -0.1700

Data Index: 1416321 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 3.3047. Min Range: -3.3047

Max Act: 3.0922. Min Act: -0.1700

Data Index: 1426184 (Python Code)

Max Activating Token Index: 750